Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

VPTQ, A Flexible and Extreme low-bit quantization algorithm

aider is AI pair programming in your terminal

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

YuE: Open Full-song Generation Foundation Model, something similar to Suno.ai but open

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and <think> tag filtering. Perfect for using advanced models wi…

🚀 豆包大模型逆向API【特长：超强联网搜索】，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。

A Python implementation of global optimization with gaussian processes.

🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

HunyuanVideo: A Systematic Framework For Large Video Generation Model

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

BS::thread_pool: a fast, lightweight, modern, and easy-to-use C++17 / C++20 / C++23 thread pool library

Implements harmful/harmless refusal removal using pure HF Transformers

A lightweight multilingual LLM

An easy-to-use library for quantizing LLMs

Enforce the output format (JSON Schema, Regex etc) of a language model

A fast inference library for running LLMs locally on modern consumer-class GPUs

A high-throughput and memory-efficient inference and serving engine for LLMs

Auto convert transformers models to QuaRot.

A high-throughput and memory-efficient inference and serving engine for LLMs

Structured Outputs

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…